Abstract
Natural language meanings allow speakers to encode important real-world distinctions, but corpora of grounded language use also reveal that speakers categorize the world in different ways and describe situations with different terminology. To learn meanings from data, we therefore need to link underlying representations of meaning to models of speaker judgment and speaker choice. This paper describes a new approach to this problem: we model variability through uncertainty in categorization boundaries and distributions over preferred vocabulary. We apply the approach to a large data set of color descriptions, where statistical evaluation documents its accuracy. The results are available as a Lexicon of Uncertain Color Standards (LUX), which supports future efforts in grounded language understanding and generation by probabilistically mapping 829 English color descriptions to potentially context-sensitive regions in HSV color space.
Highlights
Which supports future efforts in grounded language understanding and generation by probabilistically mapping 829 English color descriptions to potentially context-sensitive regions in HSV color space
In formal semantics, one of the hallmarks of for this complexity by deriving one definitive map- vague language is that speakers can make it more ping between words and the world
Our evaluation shows that LUX provides a precise description of speakers’ free-text labels of color patches
Summary
Which supports future efforts in grounded language understanding and generation by probabilistically mapping 829 English color descriptions to potentially context-sensitive regions in HSV color space. To ground natural language semantics in real-world die. There’s little reason to the choice of how to categorize and describe real- think that this variability conceals consistent meanworld data varies across people. In formal semantics, one of the hallmarks of for this complexity by deriving one definitive map- vague language is that speakers can make it more ping between words and the world. Precise in alternative, incompatible ways (Barker, We see this complexity already in free text de- 2002). We see this in practice as well, for examscriptions of color patches.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Transactions of the Association for Computational Linguistics
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.